Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/avelikiy/great_cto/skillifygit clone --depth 1 https://github.com/avelikiy/great_ctoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/avelikiy/great_cto/skillify)<a href="https://agentmods.dev/commands/avelikiy/great_cto/skillify"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/skillify.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01343 |
| Opus 5 | $0.00020 | $0.00672 |
| Sonnet 5 | $0.00008 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
skillify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Skillify command. Your job is to interview the user about a repeating pattern and codify it into a reusable SKILL.md file so agents learn the pattern permanently.
Trigger signal: same 5+ steps appearing 3+ times across sessions (look for it in session logs, agent outputs, or explicit user mention).
Step 1 — Identify the pattern
If $ARGUMENTS is provided, use it as the skill name/topic.
Otherwise, scan for candidates:
# Find repeated patterns in session logs
grep -h "Step\|1\.\|2\.\|3\." .great_cto/logs/session-*.md 2>/dev/null | sort | uniq -c | sort -rn | head -20
# Find repeated command sequences in lessons.md
cat .great_cto/lessons.md 2>/dev/null | head -50
# Recent agent outputs that looked procedural
ls .great_cto/verdicts/*.log 2>/dev/null | tail -5 | xargs grep -l "Step\|Procedure\|Checklist" 2>/dev/null
Present top 3 candidates to user. Ask: "Which pattern should I capture?"
Step 2 — Interview (one question at a time)
Ask these questions in order. Wait for an answer before asking the next.
Q1: "What triggers this pattern? Describe the situation where you'd reach for it — what keyword or signal in a request would make an agent apply this skill?"
Q2: "Walk me through the steps. Number them — I'll turn them into the skill body."
Q3: "What's the output? What artifact, verdict, or state change does completing this pattern produce?"
Q4: "Who runs this? Which agent(s) in the pipeline would apply it? (architect / pm / senior-dev / qa-engineer / security-officer / l3-support / devops / all)"
Q5: "What's the effort level? (low = <10 min of LLM work / medium = 10-30 min / high = >30 min)"
Q6: "Any anti-patterns — things this skill should actively prevent agents from doing?"
After all answers: show a draft and ask "Does this look right? Anything to add or change?"
Step 3 — Generate SKILL.md
Derive the skill slug from the name: lowercase, hyphen-separated, no special chars.
SKILL_NAME=$(echo "$ARGUMENTS" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | sed 's/[^a-z0-9-]//g')
SKILL_DIR="skills/$SKILL_NAME"
mkdir -p "$SKILL_DIR"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 148 lines · 41 tokens per session scan A 56ebf100da4f
skillify is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,343 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
develop
Implement skill development issues with TDD-governed workflow.
pb-today
Delegate to oh-my-personal-best:session-coach to prescribe today's session.
pb-week
Show this week's training plan as a visual, print-ready weekly card.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
task
Command "task" from d4rkNinja/infynon-cli, covering task, when to use, basic usage, common commands and important options.
workspace
Use workspace to manage project locations, folder aliases, model slots, and the agent root.